187 citations · 257 across the 27 of their papers we have counts for
12 papers · 1 filter
Learning from Repaired Reasoning: Root-Cause-Guided On-Policy Distillation
Chenglei Shen, Haoyang Yao, Weijie Yu +3
On-policy self-distillation (OPSD) uses reference solutions as privileged hindsight to supervise student-generated reasoning trajectories. However, reference-based guidance may exp…
Towards Understanding Continual Factual Knowledge Acquisition of Language Models: From Theory to Algorithm
Haoyu Wang, Yifan Shang, Zhongxiang Sun +3
Continual Pre-Training (CPT) is essential for enabling Language Models (LMs) to integrate new knowledge without erasing old. While classical CPT techniques like data replay have be…
Hidden States Know Where Reasoning Diverges: Credit Assignment via Span-Level Wasserstein Distance
Xinzhu Chen, Wei He, Huichuan Fan +7
Group Relative Policy Optimization (GRPO) performs coarse-grained credit assignment in reinforcement learning with verifiable rewards (RLVR) by assigning the same advantage to all…
Deep Search with Hierarchical Meta-Cognitive Monitoring Inspired by Cognitive Neuroscience
Zhongxiang Sun, Qipeng Wang, Weijie Yu +3
Deep search agents powered by large language models have demonstrated strong capabilities in multi-step retrieval, reasoning, and long-horizon task execution. However, their practi…
When Personalization Misleads: Understanding and Mitigating Hallucinations in Personalized LLMs
Zhongxiang Sun, Yi Zhan, Chenglei Shen +4
Personalized large language models (LLMs) adapt model behavior to individual users to enhance user satisfaction, yet personalization can inadvertently distort factual reasoning. We…
An Explicit Syllogistic Legal Reasoning Framework for Large Language Models
Kepu Zhang, Weijie Yu, Zhongxiang Sun +1
Syllogistic reasoning is crucial for sound legal decision-making, allowing legal professionals to draw logical conclusions by applying general principles to specific case facts. Wh…
Legal Mathematical Reasoning with LLMs: Procedural Alignment through Two-Stage Reinforcement Learning
Kepu Zhang, Guofu Xie, Weijie Yu +4
Legal mathematical reasoning is essential for applying large language models (LLMs) in high-stakes legal contexts, where outputs must be both mathematically accurate and procedural…
ReARTeR: Retrieval-Augmented Reasoning with Trustworthy Process Rewarding
Zhongxiang Sun, Qipeng Wang, Weijie Yu +6
Retrieval-Augmented Generation (RAG) systems for Large Language Models (LLMs) hold promise in knowledge-intensive tasks but face limitations in complex multi-step reasoning. While…
Beyond Guilt: Legal Judgment Prediction with Trichotomous Reasoning
Kepu Zhang, Haoyue Yang, Xu Tang +2
In legal practice, judges apply the trichotomous dogmatics of criminal law, sequentially assessing the elements of the offense, unlawfulness, and culpability to determine whether a…
CitaLaw: Enhancing LLM with Citations in Legal Domain
Kepu Zhang, Weijie Yu, Sunhao Dai +1
In this paper, we propose CitaLaw, the first benchmark designed to evaluate LLMs' ability to produce legally sound responses with appropriate citations. CitaLaw features a diverse…
ReDeEP: Detecting Hallucination in Retrieval-Augmented Generation via Mechanistic Interpretability
Zhongxiang Sun, Xiaoxue Zang, Kai Zheng +5
Retrieval-Augmented Generation (RAG) models are designed to incorporate external knowledge, reducing hallucinations caused by insufficient parametric (internal) knowledge. However,…
Wasserstein Distance Regularized Sequence Representation for Text Matching in Asymmetrical Domains
Weijie Yu, Chen Xu, Jun Xu +4
One approach to matching texts from asymmetrical domains is projecting the input sequences into a common semantic space as feature vectors upon which the matching function can be r…